Railway infrastructure information verification system and method

Abstract

The invention belongs to the technical field of railway infrastructure information verification, and particularly relates to a railway infrastructure information verification system and method. According to the method, the updating frequency and the updating amplitude of the railway infrastructure information are collected and analyzed, the key information can be effectively identified and preferentially verified, and therefore the efficiency and safety of railway infrastructure maintenance are improved, the updating frequency and the updating amplitude of each reference information subset are comprehensively evaluated, the comprehensive score is generated, and the maintenance efficiency is improved. According to the method, information subsets with high updating frequency and large updating amplitude can be ensured to be verified preferentially, so that the overall information verification efficiency is improved, in addition, ordered fluctuation and unordered fluctuation can be distinguished according to the time sequence characteristics of the railway infrastructure information, the verification strategy is further refined, and the verification work is more accurate and efficient.

Description

Technical Field

[0001] The invention belongs to the technical field of railway facility information verification, and in particular relates to a railway infrastructure information verification system and method. Background Art

[0002] With the rapid development of railway infrastructure, the scale and complexity of the railway network are constantly increasing. In order to ensure the safe operation of the railway system, it is particularly important to accurately and timely verify the railway infrastructure information. However, the existing verification methods often rely on manual operation, which is inefficient and prone to human errors. Therefore, the research on automated and intelligent railway infrastructure information verification system is particularly urgent.

[0003] In the prior art, the accuracy and timeliness of railway infrastructure information are crucial to ensuring the safety and efficiency of railway transportation. However, the existing verification methods still have many shortcomings, such as cumbersome manual operations, low efficiency, and prone to human errors. In addition, the verification of different types of railway infrastructure information is often only carried out according to inherent intervals, which will undoubtedly lead to uneven distribution of verification resources and fail to achieve the optimal verification effect. Based on this, this scheme proposes a railway infrastructure information verification method to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a railway infrastructure information verification system and method, which can automatically and efficiently verify railway infrastructure information, improve the accuracy and timeliness of the verification, and thus ensure the safe operation of the railway system.

[0005] The technical solution adopted by the present invention is as follows: A railway infrastructure information verification method, comprising: According to the characteristic attributes of the acquired railway infrastructure information, the information is classified and screened to obtain multiple benchmark information subsets; Collecting update information of the railway infrastructure information in each of the benchmark information subsets, wherein the update information includes an update timestamp and update parameters; Determining the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp; Determining the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter; Comprehensively evaluate the update frequency and update amplitude of each of the benchmark information subsets to generate a comprehensive score for each of the benchmark information subsets; The respective benchmark information subsets are sorted according to the comprehensive scores, and a verification priority is assigned to each benchmark information subset according to the sorting result.

[0006] In a preferred embodiment, the step of classifying and screening the information according to the characteristic attributes of the acquired railway infrastructure information to obtain multiple reference information subsets includes: Acquire all the railway infrastructure information and characteristic attributes of all the railway infrastructure information; Classifying the railway infrastructure information under the same characteristic attribute into the same category to form multiple information categories; Performing vector encoding processing on each of the information categories to generate a plurality of reference feature vectors; Cluster analysis is performed on each of the information categories according to the benchmark feature vector to obtain multiple benchmark information subsets.

[0007] In a preferred embodiment, the step of performing cluster analysis on each of the information categories according to the benchmark feature vector to obtain a plurality of benchmark information subsets includes: Obtaining a preset number of the reference information subsets, and initializing information category center points consistent with the preset number; Assign the baseline feature vector of each information category to the nearest information category center point to form multiple initial clusters; Re-determining the information category center point based on the initial clustering, and determining the mean of all benchmark feature vectors in the initial clustering; According to the information category center points and the mean values ​​of the benchmark feature vectors determined after the initial clustering, the benchmark feature vectors of each information category are redistributed to form updated clusters; After the clustering output is updated, the steps of determining the information category center point and reallocating the benchmark feature vector are redetermined until the attribution of each information category no longer changes, thereby obtaining a plurality of stable benchmark information subsets.

[0008] In a preferred solution, the step of determining the update frequency of the railway infrastructure information in each reference information subset according to the update timestamp comprises: Obtaining an update timestamp for each railway infrastructure information in the benchmark information subset; Arrange the update timestamps according to the occurrence sequence, and based on the arrangement result of the update timestamps, collect the interval time between adjacent update timestamps and record it as the interval time to be verified; Obtaining a standard interval duration, and comparing the standard interval duration with a verification interval duration; If the to-be-checked interval is less than or equal to the standard interval, the update timestamps with a higher ranking among the adjacent update timestamps are filtered out, and the update timestamps with a lower ranking are recorded; If the to-be-verified interval duration is longer than the standard interval duration, then the adjacent update timestamps are recorded respectively; A first condition function is obtained, and the update timestamp is input into the first condition function, and an output result of the first condition function is recorded as the update frequency.

[0009] In a preferred solution, the step of determining the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter comprises: Acquire update parameters of each railway infrastructure information in the benchmark information subset, and arrange the update parameters in a time sequence of occurrence; Performing difference processing on adjacent update parameters to obtain update fluctuation parameters; Obtaining a second conditional function, inputting the update fluctuation parameter into the second conditional function, and recording an output result of the second conditional function as a conditional parameter to be verified; Outputting the time series characteristics of the update parameters according to the condition parameters to be verified, wherein the time series characteristics include orderly fluctuations and disordered fluctuations; Under the orderly fluctuation, a prediction function is obtained, and the update parameter is input into the prediction function, and the output result of the verification function is calibrated as the update amplitude; Under the disordered fluctuation, the update fluctuation parameters are arranged in order from large to small, and the update amplitude of the railway infrastructure information is calculated based on the update fluctuation parameter with the largest value.

[0010] In a preferred solution, the step of outputting the timing characteristics of the update parameters according to the condition parameters to be verified includes: Obtain the condition parameter to be verified; Obtaining a verification function, inputting the condition parameter to be verified into the verification function, and recording the output result of the verification function as the parameter to be evaluated; Obtaining updated parameters at the same time as the parameters to be evaluated, and recording them as the benchmark parameters; Performing a difference process on the reference parameter and the parameter to be evaluated to obtain a calibration difference; A verification threshold is obtained, and the verification threshold is compared with the verification difference. When the verification difference is greater than the verification threshold, the timing characteristics of the update parameters are recorded as disordered fluctuations. Otherwise, the timing characteristics of the update parameters are recorded as ordered fluctuations.

[0011] In a preferred embodiment, the orderly fluctuations include periodic fluctuations and progressive fluctuations; Under the periodic waveform, a first calculation function is obtained, and the update amplitude is input into the first calculation function to obtain the allowable update number of the railway infrastructure information; Under the progressive fluctuation, a second calculation function is obtained, and the update amplitude is input into the second calculation function to obtain the allowable update times of the railway infrastructure information; Under the disordered fluctuation, the update amplitude is input into the first calculation function to obtain the allowable update times of the railway infrastructure information.

[0012] In a preferred solution, the step of comprehensively evaluating the update frequency and update amplitude of each of the benchmark information subsets to generate a comprehensive score for each of the benchmark information subsets includes: Obtaining the update frequency, update amplitude and allowed update times of the benchmark information subset; Get the comprehensive evaluation function; Inputting the update frequency, update amplitude and allowed update times of the benchmark information subset into a comprehensive evaluation function, and recording the output result of the comprehensive evaluation function as a comprehensive score; The greater the value of the comprehensive score, the higher the verification priority of the benchmark information subset corresponding to the comprehensive score.

[0013] The present invention also provides a railway infrastructure information verification system, using the above-mentioned railway infrastructure information verification method, comprising: A data classification module, wherein the data classification module is used to classify and filter the information according to characteristic attributes of the acquired railway infrastructure information to obtain multiple benchmark information subsets; An information collection module, the information collection module is used to collect update information of the railway infrastructure information in each of the benchmark information subsets, wherein the update information includes an update timestamp and update parameters; A frequency output module, the frequency output module is used to determine the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp; an amplitude output module, the amplitude output module being used to determine the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter; A comprehensive evaluation module, which is used to comprehensively evaluate the update frequency and update amplitude of each of the benchmark information subsets to generate a comprehensive score for each of the benchmark information subsets; A hierarchical verification module is used to sort each of the benchmark information subsets according to the comprehensive score, and assign a verification priority to each of the benchmark information subsets according to the sorting result.

[0014] And, an electronic device, the electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned railway infrastructure information verification method.

[0015] The technical effects achieved by the present invention are: By collecting and analyzing the update frequency and update amplitude of railway infrastructure information, the present invention can effectively identify and prioritize the verification of key information, thereby improving the efficiency and safety of railway infrastructure maintenance. By comprehensively evaluating the update frequency and update amplitude of each benchmark information subset and generating a comprehensive score, it can ensure that those information subsets with high update frequency and large update amplitude are prioritized for verification, thereby improving the efficiency of overall information verification. In addition, the present invention can also distinguish between orderly fluctuations and disordered fluctuations according to the time series characteristics of railway infrastructure information, further refine the verification strategy, and make the verification work more accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flow chart of the method of the present invention; Figure 2 It is a schematic diagram of the system module of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0020] See also Figure 1As shown, the present invention provides a railway infrastructure information verification method, comprising: S1. Classify and filter the acquired railway infrastructure information according to its characteristic attributes to obtain multiple benchmark information subsets; S2. Collecting update information of railway infrastructure information in each benchmark information subset, wherein the update information includes an update timestamp and update parameters; S3, determining the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp; S4, determining the update range of the railway infrastructure information in each benchmark information subset according to the update parameter; S5, comprehensively evaluating the update frequency and update amplitude of each benchmark information subset to generate a comprehensive score for each benchmark information subset; S6. Sort each benchmark information subset according to the comprehensive score, and assign a verification priority to each benchmark information subset according to the sorting result.

[0021] As described in the above steps S1-S6, with the rapid development of railway infrastructure and the improvement of information level, higher requirements are put forward for the accuracy and timeliness of railway infrastructure information, so as to ensure the safe operation of railway infrastructure. In this embodiment, firstly, according to the characteristic attributes of the acquired railway infrastructure information, detailed information classification and screening are carried out to obtain multiple benchmark information subsets, and then for the railway infrastructure information in each benchmark information subset, its update information is collected, and the update information includes a specific update timestamp and related update parameters. Then, according to the update timestamp in each benchmark information subset, the update frequency of the railway infrastructure information in each subset can be determined. The update frequency reflects the frequency of information update and is used to evaluate information. At the same time, according to the update parameters in each benchmark information subset, the update amplitude of the railway infrastructure information in each subset can be determined. The update amplitude reflects the degree of information change and is used to evaluate the importance of information change. Then, according to the update frequency and update amplitude under each benchmark information subset, a comprehensive evaluation is performed on each benchmark information subset, and then a comprehensive score of each benchmark information subset can be generated. The comprehensive score can more comprehensively reflect the update status and importance of each benchmark information subset. Finally, the comprehensive score of each benchmark information subset is used for sorting. Through the sorting results, the verification priority of each benchmark information subset can be clarified, thereby realizing the hierarchical verification of railway infrastructure information and ensuring the orderly management of railway infrastructure information.

[0022] In a preferred embodiment, the steps of classifying and screening the acquired railway infrastructure information to obtain a plurality of reference information subsets include: S101. Acquire all railway infrastructure information and characteristic attributes of all railway infrastructure information; S102, classifying railway infrastructure information under the same characteristic attribute into the same category to form multiple information categories; S103, performing vector encoding processing on each information category to generate multiple reference feature vectors; S104: Perform cluster analysis on each information category according to the benchmark feature vector to obtain multiple benchmark information subsets.

[0023] As described in the above steps S101-S104, in the process of processing railway infrastructure information, it is first necessary to classify and screen the railway infrastructure information according to its characteristic attributes so as to obtain multiple benchmark information subsets. First, it is necessary to collect relevant information of all railway infrastructure, which not only covers the physical structure of the railway, such as tracks, bridges, tunnels, etc., but also includes relevant operation data, maintenance records and safety performance indicators, etc. Then, it is necessary to list the characteristic attributes of the railway infrastructure information, which can be quantitative numerical indicators or qualitative descriptive characteristics. Then, the railway infrastructure information with the same characteristic attributes is classified into the same category, and based on this, the railway infrastructure information is effectively classified to form multiple information categories. For example, all information with the same track type or the same bridge structure can be classified into the same category. After each information category is formed, it is necessary to perform vector encoding processing on the information category. Through vector encoding, the characteristic attributes of each information category can be converted into a numerical benchmark feature vector. Finally, cluster analysis is performed on each information category based on the benchmark feature vector. Through cluster analysis, information categories with similar characteristic attributes can be further grouped to form multiple benchmark information subsets.

[0024] In a preferred embodiment, the step of performing cluster analysis on each information category according to the benchmark feature vector to obtain multiple benchmark information subsets includes: Step 1, obtain the preset number of benchmark information subsets, and initialize the center points of the information categories that are consistent with the preset number; Step 2: Assign the baseline feature vector of each information category to the nearest information category center point to form multiple initial clusters; Step 3, re-determine the center point of the information category based on the initial clustering, and determine the mean of all benchmark feature vectors in the initial clustering; Step 4: According to the information category center point and the mean of the benchmark feature vector determined after the initial clustering, the benchmark feature vectors of each information category are redistributed to form an updated cluster; Step 5: After updating the clustering output, redetermine the center point of the information category and redistribute the benchmark feature vector until the attribution of each information category no longer changes, and obtain multiple stable benchmark information subsets.

[0025] As described in the above steps Step 1-Step 5, when performing information category clustering analysis based on the benchmark feature vector, it is first necessary to count the preset number of benchmark information subsets and initialize the information category center points consistent with the preset number, that is, it is necessary to pre-set the number of expected benchmark information subsets, and then initialize the information category center points according to this number, and then assign the benchmark feature vector of each information category to the nearest information category center point, thereby forming multiple initial clusters, which can be specifically achieved through the function To calculate the distance between each benchmark feature vector and the center point of each information category, where Represents the distance between each benchmark feature vector and the center point of each information category, represents the base eigenvector, The vector representation of the center point of the information category, The number of feature points represented by the vector representing the benchmark feature vector and the center point of the information class is determined. Each benchmark feature vector is assigned to the nearest center point to form a preliminary cluster. The center point of the information category is re-determined based on the initial cluster, and the mean of all benchmark feature vectors in the initial cluster is determined. At the same time, the center point of each cluster is recalculated to make it the mean position of all benchmark feature vectors in the cluster, so as to more accurately reflect the core position of each cluster. According to the information category center point and the mean of the benchmark feature vector determined after the initial clustering, the benchmark feature vectors of each information category are reallocated to form an updated cluster. The above process is repeated to redetermine the information category center point and reallocate the benchmark feature vector until the affiliation of each information category no longer changes, and multiple stable benchmark information subsets are obtained.

[0026] In a preferred embodiment, the step of determining the update frequency of the railway infrastructure information in each reference information subset according to the update timestamp includes: S301, obtaining an update timestamp of each railway infrastructure information in the reference information subset; S302, arranging the update timestamps according to the occurrence sequence, and collecting the interval time between adjacent update timestamps according to the arrangement result of the update timestamps, and recording it as the interval time to be verified; S303, obtaining a standard interval duration, and comparing the standard interval duration with the verification interval duration; If the interval to be checked is less than or equal to the standard interval, the update timestamps with an earlier position among the adjacent update timestamps are filtered out, and the update timestamps with a later position are recorded; If the interval to be verified is longer than the standard interval, the adjacent update timestamps are recorded respectively; S304: Obtain a first conditional function, input an update timestamp into the first conditional function, and record an output result of the first conditional function as an update frequency.

[0027] As described in the above steps S301-S304, in order to determine the update frequency of the railway infrastructure information in each benchmark information subset, it is first necessary to collect the update timestamp of each railway infrastructure information in the benchmark information subset to determine the specific update time point of each railway infrastructure information. At the same time, the update timestamps will be arranged in the order of occurrence, so that the time interval between each update can be clearly defined and recorded as the interval length to be verified, and then the preset standard interval length is introduced. The standard interval length is used to compare with the interval length to be verified. The comparison result can be used to determine whether the current update frequency meets the standard. If the interval length to be verified is less than or equal to the standard interval length, it means that the information is updated frequently. In this case, the information updates in adjacent update timestamps are regarded as the same update, and the update timestamps with a higher ranking are filtered out, and only the update timestamps with a lower ranking are retained. On the contrary, if the interval length to be verified is greater than the standard interval length, it means that the update frequency is normal. At this time, it is necessary to record the adjacent update timestamps separately, and then introduce the first conditional function, wherein the expression of the first conditional function is: , where Indicates the update frequency, represents the number of adjacent update timestamps, and Represents adjacent update timestamps. By inputting each update timestamp into the first condition function, the update frequency of each railway infrastructure information can be determined.

[0028] In a preferred embodiment, the step of determining the update range of the railway infrastructure information in each benchmark information subset according to the update parameter includes: S401, obtaining update parameters of each railway infrastructure information in the reference information subset, and arranging the update parameters according to the occurrence time sequence; S402, performing difference processing on adjacent update parameters to obtain update fluctuation parameters; S403, obtaining a second conditional function, inputting the update fluctuation parameter into the second conditional function, and recording the output result of the second conditional function as the conditional parameter to be verified; S404, outputting the time series characteristics of the update parameters according to the condition parameters to be verified, wherein the time series characteristics include orderly fluctuations and disordered fluctuations; Under orderly fluctuations, obtain the prediction function, input the update parameters into the prediction function, and calibrate the output result of the verification function as the update amplitude; Under disordered fluctuations, the update fluctuation parameters are arranged in order from large to small, and the update amplitude of the railway infrastructure information is calculated based on the update fluctuation parameter with the largest value.

[0029] As described in the above steps S401-S404, in order to determine the update amplitude of the railway infrastructure information in each benchmark information subset, it is first necessary to obtain the update parameters of each railway infrastructure information in the benchmark information subset, and arrange the update parameters in the order of occurrence, so as to track the change of each update parameter over time, and then perform difference processing on adjacent update parameters, and then output them as update fluctuation parameters, which can reflect the change of each railway infrastructure information at different time points, and then introduce the second conditional function to process the update fluctuation parameters, wherein the expression of the second conditional function is: , where Indicates the condition parameters to be checked. Indicates the update period of railway infrastructure information. represents the number of updated fluctuation parameters, represents the update fluctuation parameter. By calculating the second condition function, the condition parameter to be verified can be obtained. After obtaining the condition parameter to be verified, the time series characteristics of the update parameter will be output according to the condition parameter to be verified. The time series characteristics in this embodiment include ordered fluctuation and disordered fluctuation. The ordered fluctuation means that the change of the update parameter is regular, while the disordered fluctuation means that the change of the update parameter is random and there is no obvious rule to follow. For the case of ordered fluctuation, a prediction function will be introduced, and the update parameter will be input into the prediction function. The expression of the prediction function is: , where Indicates the update amplitude, Indicates the new fluctuation parameter under the current node, It represents the prediction duration. The update amplitude of the railway infrastructure information can be calibrated through the output result of the prediction function. For the case of disordered fluctuation, it is necessary to arrange the update fluctuation parameters in descending order, and calculate the update amplitude of the railway infrastructure information based on the update fluctuation parameter with the largest value. It is suitable for the case where there is no obvious regularity in the changes. By selecting the maximum fluctuation value as a reference, the update amplitude of the railway infrastructure information can be adaptively estimated.

[0030] In a preferred embodiment, the step of outputting the timing characteristics of the update parameters according to the condition parameters to be verified includes: Get the condition parameters to be verified; Obtain a verification function, input the condition parameters to be verified into the verification function, and record the output result of the verification function as the parameter to be evaluated; Obtain the updated parameters at the same time as the parameters to be evaluated, and record them as the baseline parameters; Perform difference processing on the reference parameter and the parameter to be evaluated to obtain the calibration difference; A verification threshold is obtained, and the verification threshold is compared with the verification difference. When the verification difference is greater than the verification threshold, the timing characteristics of the updated parameters are recorded as disordered fluctuations. Otherwise, the timing characteristics of the updated parameters are recorded as ordered fluctuations.

[0031] In this implementation, when outputting the timing characteristics of the update parameters, it is first necessary to obtain the condition parameters to be verified and simultaneously introduce the verification function. By inputting the condition parameters to be verified into the verification function, the parameters to be evaluated for evaluating the timing characteristics of the condition parameters to be verified can be output, wherein the expression of the verification function is: , where Indicates the calibration difference. Indicates the condition parameters to be checked. It represents the time interval between the condition parameter to be checked and the parameter to be evaluated. Based on the calculation of the verification function, the update parameter at the same time as the parameter to be evaluated is obtained and recorded as the benchmark parameter for comparison with the parameter to be evaluated. Next, the benchmark parameter and the parameter to be evaluated are subjected to difference processing. By calculating the difference between the two, the verification difference can be obtained, thereby reflecting the degree of difference between the parameter to be evaluated and the benchmark parameter. Here, it should be clear that there are multiple verification differences. Before comparing with the verification threshold, all verification differences will be summed and averaged to obtain the average verification difference. The verification threshold is a pre-set standard value used to determine whether the difference between the parameter to be evaluated and the benchmark parameter is within an acceptable range. Then the verification threshold is compared with the verification difference after the average value is calculated. If the verification difference is greater than the verification threshold, it means that the difference between the parameter to be evaluated and the benchmark parameter is too large. At this time, the timing characteristics of the update parameter will be recorded as disordered fluctuations. On the contrary, if the verification difference is less than or equal to the verification threshold, it means that the difference between the parameter to be evaluated and the benchmark parameter is within an acceptable range. At this time, the timing characteristics of the update parameter will be recorded as ordered fluctuations, thereby realizing the evaluation of the timing characteristics of the update parameter.

[0032] In a preferred embodiment, the orderly fluctuations include periodic fluctuations and progressive fluctuations; Under the periodic waveform, a first calculation function is obtained, and the update amplitude is input into the first calculation function to obtain the allowable update number of the railway infrastructure information; Under the progressive fluctuation, a second estimation function is obtained, and the update amplitude is input into the second estimation function to obtain the allowable update times of the railway infrastructure information; Under disordered fluctuations, the update amplitude is input into the first estimation function to obtain the allowable number of updates of the railway infrastructure information.

[0033] In this embodiment, the orderly fluctuation covers two different fluctuation modes: periodic fluctuation and progressive fluctuation. In the case of periodic fluctuation, the fluctuation of railway infrastructure information has a periodic law, such as seasonal changes or annual periodic fluctuations. By introducing a first calculation function and inputting a specific update amplitude value into the first calculation function, the allowable number of updates of railway infrastructure information in the periodic fluctuation mode can be calculated. The expression of the first calculation function is: (update amplitude upper limit value / update amplitude)-the number of times the railway infrastructure information has been updated. In the case of progressive fluctuation, a second calculation function is introduced to calculate the allowable number of updates of railway infrastructure information, wherein the expression of the second calculation function is: ln(update amplitude upper limit value / update amplitude) -The number of times the railway infrastructure information has been updated. Progressive fluctuations usually manifest themselves as a trend that gradually increases or decreases, such as continuous improvements brought about by technological progress or the gradual aging of infrastructure. The second measurement function can be used to evaluate the allowable number of updates of the railway infrastructure information under the progressive fluctuation mode to ensure the stability and reliability of the infrastructure in a continuously changing environment. For the case of disordered fluctuations, there is no obvious regularity in the changes in the update parameters. In this case, the update amplitude is input into the first measurement function. Although disordered fluctuations have no obvious periodic regularity, the first measurement function can still be used to estimate the allowable number of updates of the railway infrastructure information to ensure that the update of the railway infrastructure information is still within an acceptable range in the case of disordered changes.

[0034] In a preferred embodiment, the step of comprehensively evaluating the update frequency and update amplitude of each benchmark information subset to generate a comprehensive score for each benchmark information subset includes: Obtaining the update frequency, update amplitude and allowed number of updates of the benchmark information subset; Get the comprehensive evaluation function; The update frequency, update amplitude and allowed number of updates of the benchmark information subset are input into the comprehensive evaluation function, and the output result of the comprehensive evaluation function is recorded as the comprehensive score; Among them, the larger the value of the comprehensive score is, the higher the verification priority of the benchmark information subset corresponding to the comprehensive score is.

[0035] As in the above steps, after the update frequency and update amplitude of the benchmark information subset are output, a comprehensive evaluation function will be simultaneously introduced to integrate and analyze the update frequency, update amplitude and allowed number of updates of the benchmark information subset, so as to generate a comprehensive score. The expression of the comprehensive evaluation function is: comprehensive score = α*update frequency + β*update amplitude + γ*allowed number of updates, where α, β, and γ represent the weight coefficients of the update frequency, update amplitude and allowed number of updates in the comprehensive score, respectively. In addition, the weight coefficient can be adjusted according to the actual application scenario and needs to ensure that the comprehensive score can more accurately reflect the verification priority of the benchmark information subset. Specifically, the larger the value of the comprehensive score, the more ideal the update frequency and update amplitude of the benchmark information subset, and therefore the higher its verification priority. Conversely, if the comprehensive score is low, it means that the update frequency and update amplitude of the subset are not ideal, and its verification priority is relatively low, which provides reasonable resource allocation for the verification of railway infrastructure information and ensures the timeliness and effectiveness of railway infrastructure information update and maintenance.

[0036] See also Figure 2 , a railway infrastructure information verification system, using the above-mentioned railway infrastructure information verification method, comprising: A data classification module, which is used to classify and filter the acquired railway infrastructure information according to its characteristic attributes to obtain multiple benchmark information subsets; An information collection module, the information collection module is used to collect update information of railway infrastructure information in each benchmark information subset, wherein the update information includes an update timestamp and update parameters; A frequency output module, the frequency output module is used to determine the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp; An amplitude output module, the amplitude output module is used to determine the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter; A comprehensive evaluation module is used to comprehensively evaluate the update frequency and update amplitude of each benchmark information subset and generate a comprehensive score for each benchmark information subset; The hierarchical verification module is used to sort each benchmark information subset according to the comprehensive score, and assign a verification priority to each benchmark information subset according to the sorting result.

[0037] In the above, the system includes a data classification module, an information acquisition module, a frequency output module, an amplitude output module, a comprehensive evaluation module and a hierarchical verification module. The data classification module is responsible for the detailed classification and screening of the acquired railway infrastructure information. By analyzing the characteristic attributes of the information, the original data set can be divided into multiple benchmark information subsets with specific characteristics. The information acquisition module is responsible for the real-time collection of railway infrastructure information update information in each benchmark information subset. The update information includes update timestamps and update parameters to ensure that the system can grasp the latest status of the information in a timely manner. The frequency output module focuses on analyzing the update timestamp to determine the update frequency of the railway infrastructure information in each benchmark information subset. In this way, the system can understand each The update frequency of each benchmark information subset is used to optimize resource allocation. The amplitude output module evaluates the update amplitude of the railway infrastructure information in each benchmark information subset based on the update parameters. The comprehensive evaluation module is responsible for comprehensively evaluating the update frequency and update amplitude under each benchmark information subset, and generating a corresponding comprehensive score. The comprehensive score reflects the overall update status of each benchmark information subset, and provides a prerequisite for the subsequent allocation of verification resources. The hierarchical verification module sorts each benchmark information subset according to the comprehensive score. In this way, the system can assign different verification priorities to each benchmark information subset to ensure that the information subset with high update frequency and large update amplitude can be verified first, thereby improving the efficiency and accuracy of the overall verification work.

[0038] See also Figure 3 , an electronic device, the electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned railway infrastructure information verification method.

[0039] The processor of the above-mentioned electronic device may be a central processing unit (CPU) or a graphics processing unit (GPU), which is responsible for executing the computer program stored in the memory. The memory may be a random access memory (RAM), a read-only memory (ROM) or other types of storage media, which is used to store computer programs and related data. The electronic device also includes an arithmetic unit, an input device and an output device. The arithmetic unit is responsible for executing the instructions issued by the processor, performing data processing and computing tasks. The input device provides the user with a means of interacting with the electronic device, such as a keyboard, a mouse, a touch screen, etc. The output device presents the processing results to the user, such as a display, a printer, etc. In practical applications, the electronic device may be a special device specially designed for railway infrastructure information verification, or a general-purpose computer system.

[0040] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0041] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A railway infrastructure information verification method, characterized in that: include: According to the characteristic attributes of the acquired railway infrastructure information, the information is classified and screened to obtain multiple benchmark information subsets; Collecting update information of the railway infrastructure information in each of the benchmark information subsets, wherein the update information includes an update timestamp and update parameters; Determining the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp; Determining the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter; Comprehensively evaluate the update frequency and update amplitude of each of the benchmark information subsets to generate a comprehensive score for each of the benchmark information subsets; The respective benchmark information subsets are sorted according to the comprehensive scores, and a verification priority is assigned to each benchmark information subset according to the sorting result.

2. A railway infrastructure information verification method according to claim 1, characterized in that: The step of classifying and screening the information according to the characteristic attributes of the acquired railway infrastructure information to obtain multiple benchmark information subsets includes: Acquire all the railway infrastructure information and characteristic attributes of all the railway infrastructure information; Classifying the railway infrastructure information under the same characteristic attribute into the same category to form multiple information categories; Performing vector encoding processing on each of the information categories to generate a plurality of reference feature vectors; Cluster analysis is performed on each of the information categories according to the benchmark feature vector to obtain multiple benchmark information subsets.

3. A railway infrastructure information verification method according to claim 2, characterized in that: The step of performing cluster analysis on each of the information categories according to the benchmark feature vector to obtain a plurality of benchmark information subsets includes: Obtaining a preset number of the reference information subsets, and initializing information category center points consistent with the preset number; Assign the baseline feature vector of each information category to the nearest information category center point to form multiple initial clusters; Re-determining the information category center point based on the initial clustering, and determining the mean of all benchmark feature vectors in the initial clustering; According to the information category center points and the mean values ​​of the benchmark feature vectors determined after the initial clustering, the benchmark feature vectors of each information category are redistributed to form updated clusters; After the clustering output is updated, the steps of determining the information category center point and reallocating the benchmark feature vector are redetermined until the attribution of each information category no longer changes, thereby obtaining a plurality of stable benchmark information subsets.

4. A railway infrastructure information verification method according to claim 1, characterized in that: The step of determining the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp comprises: Obtaining an update timestamp for each railway infrastructure information in the benchmark information subset; Arrange the update timestamps according to the occurrence sequence, and based on the arrangement result of the update timestamps, collect the interval time between adjacent update timestamps and record it as the interval time to be verified; Obtaining a standard interval duration, and comparing the standard interval duration with a verification interval duration; If the to-be-checked interval is less than or equal to the standard interval, the update timestamps with a higher ranking among the adjacent update timestamps are filtered out, and the update timestamps with a lower ranking are recorded; If the to-be-verified interval duration is longer than the standard interval duration, then the adjacent update timestamps are recorded respectively; A first condition function is obtained, and the update timestamp is input into the first condition function, and an output result of the first condition function is recorded as the update frequency.

5. A railway infrastructure information verification method according to claim 1, characterized in that: The step of determining the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter comprises: Acquire update parameters of each railway infrastructure information in the benchmark information subset, and arrange the update parameters in a time sequence of occurrence; Performing difference processing on adjacent update parameters to obtain update fluctuation parameters; Obtaining a second conditional function, inputting the update fluctuation parameter into the second conditional function, and recording an output result of the second conditional function as a conditional parameter to be verified; Outputting the time series characteristics of the update parameters according to the condition parameters to be verified, wherein the time series characteristics include orderly fluctuations and disordered fluctuations; Under the orderly fluctuation, a prediction function is obtained, and the update parameter is input into the prediction function, and the output result of the verification function is calibrated as the update amplitude; Under the disordered fluctuation, the update fluctuation parameters are arranged in order from large to small, and the update amplitude of the railway infrastructure information is calculated based on the update fluctuation parameter with the largest value.

6. A railway infrastructure information verification method according to claim 1, characterized in that: The step of outputting the timing characteristics of the update parameters according to the condition parameters to be checked includes: Obtain the condition parameter to be verified; Obtaining a verification function, inputting the condition parameter to be verified into the verification function, and recording the output result of the verification function as the parameter to be evaluated; Obtaining updated parameters at the same time as the parameters to be evaluated, and recording them as the benchmark parameters; Performing a difference process on the reference parameter and the parameter to be evaluated to obtain a calibration difference; A verification threshold is obtained, and the verification threshold is compared with the verification difference. When the verification difference is greater than the verification threshold, the timing characteristics of the update parameters are recorded as disordered fluctuations. Otherwise, the timing characteristics of the update parameters are recorded as ordered fluctuations.

7. A railway infrastructure information verification method according to claim 6, characterized in that: The orderly fluctuations include periodic fluctuations and progressive fluctuations; Under the periodic waveform, a first calculation function is obtained, and the update amplitude is input into the first calculation function to obtain the allowable update number of the railway infrastructure information; Under the progressive fluctuation, a second calculation function is obtained, and the update amplitude is input into the second calculation function to obtain the allowable update times of the railway infrastructure information; Under the disordered fluctuation, the update amplitude is input into the first calculation function to obtain the allowable update times of the railway infrastructure information.

8. A railway infrastructure information verification method according to claim 7, characterized in that: The step of comprehensively evaluating the update frequency and update amplitude of each of the benchmark information subsets to generate a comprehensive score for each of the benchmark information subsets includes: Obtaining the update frequency, update amplitude and allowed update times of the benchmark information subset; Get the comprehensive evaluation function; Inputting the update frequency, update amplitude and allowed update times of the benchmark information subset into a comprehensive evaluation function, and recording the output result of the comprehensive evaluation function as a comprehensive score; The greater the value of the comprehensive score, the higher the verification priority of the benchmark information subset corresponding to the comprehensive score.

9. A railway infrastructure information verification system, characterized by: The railway infrastructure information verification method according to any one of claims 1 to 8 comprises: A data classification module, wherein the data classification module is used to classify and filter the information according to characteristic attributes of the acquired railway infrastructure information to obtain multiple benchmark information subsets; An information collection module, the information collection module is used to collect update information of the railway infrastructure information in each of the benchmark information subsets, wherein the update information includes an update timestamp and update parameters; A frequency output module, the frequency output module is used to determine the update frequency of the railway infrastructure information in each benchmark information subset according to the update timestamp; an amplitude output module, the amplitude output module being used to determine the update amplitude of the railway infrastructure information in each benchmark information subset according to the update parameter; A comprehensive evaluation module, which is used to comprehensively evaluate the update frequency and update amplitude of each of the benchmark information subsets to generate a comprehensive score for each of the benchmark information subsets; A hierarchical verification module is used to sort each of the benchmark information subsets according to the comprehensive score, and assign a verification priority to each of the benchmark information subsets according to the sorting result.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the railway infrastructure information verification method described in any one of claims 1 to 8.

Images